derivation_get_step

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the returned content in bullet points and provides a concrete example showing a success response, making the tool's behavior predictable. It does not discuss error cases or side effects, but 'get' implies read-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with the purpose, and uses clear headings (Args, Returns, Example) along with bullets. Every line adds value with no unnecessary content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core functionality and includes an example, but it lacks context on session_id and how the step relates to a derivation session. Given no annotations and the existence of many session-related sibling tools, this is a gap that could confuse an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning to step_number by specifying it is 1-based, and the example indicates session_id is optional. However, session_id is not explained at all, and with 0% schema coverage, this is a notable gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states '取得單一步驟的詳細資訊' (retrieve detailed information for a single step) and enumerates the specific content fields returned (operation type, input/output expressions, SymPy commands, human knowledge). This distinguishes it from sibling tools like derivation_get_steps, which retrieve multiple steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says '用於檢視特定步驟的完整記錄' (used to view the complete record of a specific step), providing explicit context for when the tool is appropriate. It does not mention alternatives or exclusions, but the singular scope is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.